Automated segmentation and classification of high throughput yeast assay spots

Automated segmentation of mouse brain images using extended MRF

We introduce an automated segmentation method, extended Markov random field (eMRF), to classify 21 neuroanatomical structures of mouse brain based on three dimensional (3D) magnetic resonance images (MRI). The image data are multispectral: T2-weighted, proton density-weighted, diffusion x, y and z weighted. Earlier research (Ali, A.A., Dale, A.M., Badea, A., Johnson, G.A., 2005. Automated segmentation of neuroanatomical structures in multispectral MR microscopy of the mouse brain. NeuroImage 27 (2), 425-435) successfully explored the use of MRF for mouse brain segmentation. In this research, we study the use of information generated from support vector machine (SVM) to represent the probabilistic information. Since SVM in general has a stronger discriminative power than the Gaussian likelihood method and is able to handle nonlinear classification problems, integrating SVM into MRF improved the classification accuracy. The eMRF employs the posterior probability distribution obtained from SVM to generate a classification based on the MR intensity. Secondly, the eMRF introduces a new potential function based on location information. Third, to maximize the classification performance, the eMRF uses the contribution weights optimally determined for each of the three potential functions: observation, location and contextual functions, which are traditionally equally weighted. We use the voxel overlap percentage and volume difference percentage to evaluate the accuracy of eMRF segmentation and compare the algorithm with three other segmentation methods--mixed ratio sampling SVM (MRS-SVM), atlas-based segmentation and MRF. Validation using classification accuracy indices between automatically segmented and manually traced data shows that eMRF outperforms other methods.

Arterial spin-labeled perfusion combined with segmentation techniques to evaluate cerebral blood flow in white and gray matter of children with sickle cell anemia

BACKGROUND

Changes in cerebral perfusion are an important feature of the pathophysiology of sickle cell anemia (SCA); cerebrovascular ischemia occurs frequently and leads to neurocognitive deficits, silent infarcts, and overt stroke. Non-invasive MRI methods to measure cerebral blood flow (CBF) by arterial spin labeling (ASL) afford new opportunities to characterize disease- and therapy-induced changes in cerebral hemodynamics in patients with SCA. Recent studies have documented elevated gray matter (GM) CBF in untreated children with SCA, but no measurements of white matter (WM) CBF have been reported.

PROCEDURES

Pulsed ASL with automated brain image segmentation-classification techniques were used to determine the CBF in GM, WM, and abnormal white matter (ABWM) of 21 children with SCA, 18 of whom were receiving hydroxyurea therapy.

RESULTS

GM and WM CBF were highly associated (R(2) = 0.76, P < 0.0001) and the GM to WM CBF ratio was 1.6 (95% confidence interval: 1.43-1.83). Global GM CBF in our treated cohort was 87 +/- 24 mL/min/100 g, a value lower than previously reported in untreated patients with SCA. CBF was elevated in normal appearing WM (43 +/- 14 mL/min/100 g) but decreased in ABWM (6 +/- 12 mL/min/100 g), compared to published normal pediatric controls. Hemispheric asymmetry in CBF was noted in most patients.

CONCLUSIONS

These perfusion measurements suggest that hydroxyurea may normalize GM CBF in children with SCA, but altered perfusion in WM may persist. This novel combined approach for CBF quantification will facilitate prospective studies of cerebral vasculopathy in SCA, particularly regarding the effects of treatments such as hydroxyurea.

A wavelet-based optimal texture feature set for classification of brain tumours

In this work, the classification of brain tumours in magnetic resonance images is studied by using optimal texture features. These features are used to classify three sets of brain images - normal brain, benign tumour and malignant tumour. A wavelet-based texture feature set is derived from the region of interest. Each selected brain region of interest is characterized with both its energy and texture features extracted from the selected high frequency subband. An artificial neural network classifier is employed to evaluate the performance of these features. Feature selection is performed by a genetic algorithm. Principal component analysis and classical sequential methods are compared against the genetic approach in terms of the best recognition rate achieved and the optimal number of features. A classification performance of 98% is achieved in a genetic algorithm with only four of the available 29 features. Principal component analysis and classical sequential methods require a larger feature set to attain the similar classification accuracy of 98%. The optimal texture features such as range of angular second moment, range of sum variance, range of information measure of correlation II and energy selected by the genetic algorithm provide best classification performance with lower computational effort.

Artificial neural network: border detection in echocardiography

Being non-invasive and low cost, the echocardiography has become a diagnostic technique largely applied for the determination of the left ventricle systolic and diastolic volumes, which are used indirectly to calculate the left ventricle ejection volume, the cardiac cavities muscular contraction, the regional ejection fraction, the myocardial thickness, and the ventricular mass, etc. However, the image is very noisy, which renders the delineation of the borders of the left ventricle very difficult. While there are many techniques image segmentation, this work chooses the artificial neural network (ANN) since it is not very sensitive to noise. In order to reduce the processing time, the operator selects the region of interest where the neural network will identify the borders. Neighborhood and gradient search techniques are then employed to link the points and the left ventricle contour is traced. The present method has been efficient in detecting the left ventricle borders echocardiography images compared to those whose borders were delineated by the specialists. For good results, it is important to choose properly the areas to be analyzed and the central points of these areas.

Fast nosological imaging using canonical correlation analysis of brain data obtained by two-dimensional turbo spectroscopic imaging

A new fast and accurate tissue typing technique has recently been successfully applied to prostate MR spectroscopic imaging (MRSI) data. This technique is based on canonical correlation analysis (CCA), a statistical method able to simultaneously exploit the spectral and spatial information characterizing the MRSI data. Here, the performance of CCA is further investigated by using brain data obtained by two-dimensional turbo spectroscopic imaging (2DTSI) from patients affected by glioblastoma. The purpose of this study is to investigate the applicability of CCA when typing tissues of heterogeneous tumors. The performance of CCA is also compared with that of ordinary correlation analysis on simulated as well as in vivo data. The results show that CCA outperforms ordinary correlation analysis in terms of robustness and accuracy.

Automated bony region identification using artificial neural networks: reliability and validation measurements

OBJECTIVE

The objective was to develop tools for automating the identification of bony structures, to assess the reliability of this technique against manual raters, and to validate the resulting regions of interest against physical surface scans obtained from the same specimen.

MATERIALS AND METHODS

Artificial intelligence-based algorithms have been used for image segmentation, specifically artificial neural networks (ANNs). For this study, an ANN was created and trained to identify the phalanges of the human hand.

RESULTS

The relative overlap between the ANN and a manual tracer was 0.87, 0.82, and 0.76, for the proximal, middle, and distal index phalanx bones respectively. Compared with the physical surface scans, the ANN-generated surface representations differed on average by 0.35 mm, 0.29 mm, and 0.40 mm for the proximal, middle, and distal phalanges respectively. Furthermore, the ANN proved to segment the structures in less than one-tenth of the time required by a manual rater.

CONCLUSIONS

The ANN has proven to be a reliable and valid means of segmenting the phalanx bones from CT images. Employing automated methods such as the ANN for segmentation, eliminates the likelihood of rater drift and inter-rater variability. Automated methods also decrease the amount of time and manual effort required to extract the data of interest, thereby making the feasibility of patient-specific modeling a reality.

Registration and machine learning-based automated segmentation of subcortical and cerebellar brain structures

The large amount of imaging data collected in several ongoing multi-center studies requires automated methods to delineate brain structures of interest. We have previously reported on using artificial neural networks (ANN) to define subcortical brain structures. Here we present several automated segmentation methods using multidimensional registration. A direct comparison between template, probability, artificial neural network (ANN) and support vector machine (SVM)-based automated segmentation methods is presented. Three metrics for each segmentation method are reported in the delineation of subcortical and cerebellar brain regions. Results show that the machine learning methods outperform the template and probability-based methods. Utilization of these automated segmentation methods may be as reliable as manual raters and require no rater intervention.

Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification

Conventional k-Nearest-Neighbor (kNN) classification, which has been successfully applied to classify brain tissue in MR data, requires training on manually labeled subjects. This manual labeling is a laborious and time-consuming procedure. In this work, a new fully automated brain tissue classification procedure is presented, in which kNN training is automated. This is achieved by non-rigidly registering the MR data with a tissue probability atlas to automatically select training samples, followed by a post-processing step to keep the most reliable samples. The accuracy of the new method was compared to rigid registration-based training and to conventional kNN-based segmentation using training on manually labeled subjects for segmenting gray matter (GM), white matter (WM) and cerebrospinal fluid (CSF) in 12 data sets. Furthermore, for all classification methods, the performance was assessed when varying the free parameters. Finally, the robustness of the fully automated procedure was evaluated on 59 subjects. The automated training method using non-rigid registration with a tissue probability atlas was significantly more accurate than rigid registration. For both automated training using non-rigid registration and for the manually trained kNN classifier, the difference with the manual labeling by observers was not significantly larger than inter-observer variability for all tissue types. From the robustness study, it was clear that, given an appropriate brain atlas and optimal parameters, our new fully automated, non-rigid registration-based method gives accurate and robust segmentation results. A similarity index was used for comparison with manually trained kNN. The similarity indices were 0.93, 0.92 and 0.92, for CSF, GM and WM, respectively. It can be concluded that our fully automated method using non-rigid registration may replace manual segmentation, and thus that automated brain tissue segmentation without laborious manual training is feasible.

Quantitative morphologic evaluation of magnetic resonance imaging during and after treatment of childhood leukemia

INTRODUCTION

Medical advances over the last several decades, including CNS prophylaxis, have greatly increased survival in children with leukemia. As survival rates have increased, clinicians and scientists have been afforded the opportunity to further develop treatments to improve the quality of life of survivors by minimizing the long-term adverse effects. When evaluating the effect of antileukemia therapy on the developing brain, magnetic resonance (MR) imaging has been the preferred modality because it quantifies morphologic changes objectively and noninvasively.

METHOD AND RESULTS

Computer-aided detection of changes on neuroimages enables us to objectively differentiate leukoencephalopathy from normal maturation of the developing brain. Quantitative tissue segmentation algorithms and relaxometry measures have been used to determine the prevalence, extent, and intensity of white matter changes that occur during therapy. More recently, diffusion tensor imaging has been used to quantify microstructural changes in the integrity of the white matter fiber tracts. MR perfusion imaging can be used to noninvasively monitor vascular changes during therapy. Changes in quantitative MR measures have been associated, to some degree, with changes in neurocognitive function during and after treatment.

CONCLUSION

In this review, we present recent advances in quantitative evaluation of MR imaging and discuss how these methods hold the promise to further elucidate the pathophysiologic effects of treatment for childhood leukemia.

Segmentation and grading of brain tumors on apparent diffusion coefficient images using self-organizing maps

An accurate computer-assisted method to perform segmentation of brain tumor on apparent diffusion coefficient (ADC) images and evaluate its grade (malignancy state) has been designed using a mixture of unsupervised artificial neural networks (ANN) and hierarchical multiresolution wavelet. Firstly, the ADC images are decomposed by multiresolution wavelets, which are subsequently selectively reconstructed to form wavelet filtered images. These wavelet filtered images along with FLAIR and T2 weighted images have been utilized as the features to unsupervised neural network - self organizing maps (SOM) - to segment the tumor, edema, necrosis, CSF and normal tissue and grade the malignant state of the tumor. A novel segmentation algorithm based on the number of hits experienced by Best Matching Units (BMU) on SOM maps is proposed. The results shows that the SOM performs well in differentiating the tumor, edema, necrosis, CSF and normal tissue pattern vectors on ADC images. Using the trained SOM and proposed segmentation algorithm, we are able to identify high or low grade tumor, edema, necrosis, CSF and normal tissue. The results are validated against manually segmented images and sensitivity and the specificity are observed to be 0.86 and 0.93, respectively.

A neural network approach for image reconstruction in electron magnetic resonance tomography

An object-oriented, artificial neural network (ANN) based, application system for reconstruction of two-dimensional spatial images in electron magnetic resonance (EMR) tomography is presented. The standard back propagation algorithm is utilized to train a three-layer sigmoidal feed-forward, supervised, ANN to perform the image reconstruction. The network learns the relationship between the 'ideal' images that are reconstructed using filtered back projection (FBP) technique and the corresponding projection data (sinograms). The input layer of the network is provided with a training set that contains projection data from various phantoms as well as in vivo objects, acquired from an EMR imager. Twenty five different network configurations are investigated to test the ability of the generalization of the network. The trained ANN then reconstructs two-dimensional temporal spatial images that present the distribution of free radicals in biological systems. Image reconstruction by the trained neural network shows better time complexity than the conventional iterative reconstruction algorithms such as multiplicative algebraic reconstruction technique (MART). The network is further explored for image reconstruction from 'noisy' EMR data and the results show better performance than the FBP method. The network is also tested for its ability to reconstruct from limited-angle EMR data set.

Magnetic resonance imaging segmentation techniques using batch-type learning vector quantization algorithms

In this article, we propose batch-type learning vector quantization (LVQ) segmentation techniques for the magnetic resonance (MR) images. Magnetic resonance imaging (MRI) segmentation is an important technique to differentiate abnormal and normal tissues in MR image data. The proposed LVQ segmentation techniques are compared with the generalized Kohonen's competitive learning (GKCL) methods, which were proposed by Lin et al. [Magn Reson Imaging 21 (2003) 863-870]. Three MRI data sets of real cases are used in this article. The first case is from a 2-year-old girl who was diagnosed with retinoblastoma in her left eye. The second case is from a 55-year-old woman who developed complete left side oculomotor palsy immediately after a motor vehicle accident. The third case is from an 84-year-old man who was diagnosed with Alzheimer disease (AD). Our comparisons are based on sensitivity of algorithm parameters, the quality of MRI segmentation with the contrast-to-noise ratio and the accuracy of the region of interest tissue. Overall, the segmentation results from batch-type LVQ algorithms present good accuracy and quality of the segmentation images, and also flexibility of algorithm parameters in all the comparison consequences. The results support that the proposed batch-type LVQ algorithms are better than the previous GKCL algorithms. Specifically, the proposed fuzzy-soft LVQ algorithm works well in segmenting AD MRI data set to accurately measure the hippocampus volume in AD MR images.

A knowledge-guided active model method of cortical structure segmentation on pediatric MR images

PURPOSE

To develop an automated method for quantification of cortical structures on pediatric MR images.

MATERIALS AND METHODS

A knowledge-guided active model (KAM) approach was proposed with a novel object function similar to the Gibbs free energy function. Triangular mesh models were transformed to images of a given subject by maximizing entropy, and then actively slithered to boundaries of structures by minimizing enthalpy. Volumetric results and image similarities of 10 different cortical structures segmented by KAM were compared with those traced manually. Furthermore, the segmentation performances of KAM and SPM2, (statistical parametric mapping, a MATLAB software package) were compared.

RESULTS

The averaged volumetric agreements between KAM- and manually-defined structures (both 0.95 for structures in healthy children and children with medulloblastoma) were higher than the volumetric agreement for SPM2 (0.90 and 0.80, respectively). The similarity measurements (kappa) between KAM- and manually-defined structures (0.95 and 0.93, respectively) were higher than those for SPM2 (both 0.86).

CONCLUSION

We have developed a novel automatic algorithm, KAM, for segmentation of cortical structures on MR images of pediatric patients. Our preliminary results indicated that when segmenting cortical structures, KAM was in better agreement with manually-delineated structures than SPM2. KAM can potentially be used to segment cortical structures for conformal radiation therapy planning and for quantitative evaluation of changes in disease or abnormality.

Estimation of white matter connectivity based on a three-dimensional directional diffusion function in diffusion tensor MRI

Diffusion tensor (DT) magnetic resonance imaging (MRI) provides the directional information of local neuronal fibers, and has been used to estimate the neuroanatomical connectivity in the cerebral white matter. Several methods for white matter tractography have been developed based on DT-MRI. However, it has been difficult to estimate the white matter tract pathways in the fiber crossing and branching region because of the ambiguity of the principal eigenvector and/or low anisotropy due to the partial volume effect. In this paper, we proposed a new method for white matter tractography, which permits fiber tract branching and passing through crossing regions. Our tractography method is based on a three-dimensional (3D) directional diffusion function (DDF), which was given by a 3D anisotropic Gaussian function defined by normalized three eigenvalues and their corresponding eigenvectors of DT. The DDF was used for generation of a 3D directional diffusion field and for determination of the connectivity between the voxels in fiber tracking. To extract the white matter tract region, DDF-based tractography (DDFT) method used the directional diffusion field instead of a threshold fractional anisotropy map, which has been used in the conventional methods, so that low anisotropy voxels in the branching and crossing regions may be included. We applied the DDFT method and two conventional tractography methods (a streamline technique and a tensorline algorithm) to DT-MRI data of five normal subjects for visualizing the pyramidal tract. Our method visualized the pathways connected to a large portion of the primary motor cortex, including foot, hand and face motor areas, passing through the crossing regions with other white matter tracts in all subjects, whereas the conventional methods showed only a small portion of the pyramidal tract. The pyramidal tract pathways estimated by our method were consistent with the neuroanatomical knowledge. In conclusion, the DDFT method may be useful in assisting neuroradiologists in estimating the white matter tracts.

A novel, fast entropy-minimization algorithm for bias field correction in MR images

A novel, fast entropy-minimization algorithm for bias field correction in magnetic resonance (MR) images is suggested to correct the intensity inhomogeneity degradation of MR images that has become an increasing problem with the use of phased-array coils. Four important modifications were made to the conventional algorithm: (a) implementation of a modified two-step sampling strategy for stacked 2D image data sets, which included reducing the size of the measured image on each slice with a simple averaging method without changing the number of slices and then using a binary mask generated by a histogram threshold method to define the sampled voxels in the reduced image; (b) improvement of the efficiency of the correction function by using a Legendre polynomial as an orthogonal base function polynomial; (c) use of a nonparametric Parzen window estimator with a Gaussian kernel to calculate the probability density function and Shannon entropy directly from the image data; and (d) performing entropy minimization with a conjugate gradient method. Results showed that this algorithm could correct different types of MR images from different types of coils acquired at different field strengths very efficiently and with decreased computational load.

Quantitative morphologic evaluation of white matter in survivors of childhood medulloblastoma

In survivors of pediatric brain tumors, cranial radiation therapy can cause a debilitating cognitive decline associated with decreased volume in normal-appearing white matter (NAWM). We applied fractal geometry to quantify white matter (WM) integrity in the brain of medulloblastoma survivors. Fractal features of WM were evaluated by indices of fractal dimensions (FDs) of WM intensity and boundary on T1-weighted magnetic resonance images. The FD index of WM intensity was calculated by using a fractional Brownian motion model, and the FD index of WM boundary was calculated by using a box-counting method. Fractal features of WM on 116 magnetic resonance images of 58 patients with medulloblastoma were investigated at the start of therapy (Start TX) and approximately 2 years later (After TX). Patients were assigned to one of two groups based on change in NAWM volumes. Fractal features in patients with decreased NAWM volume were significantly greater After TX, whereas those in patients with increased NAWM volumes were not. Multiple linear regression analysis showed that fractal features were strongly correlated with NAWM volumes After TX in patients with decreased NAWM volume. These results demonstrated significant deficit in NAWM integrity and WM density changes in children treated for medulloblastoma. Multiple regression analysis illustrated that deficits in NAWM integrity in these children may partly explain the decrease in NAWM volume. We conclude that fractal geometry can be used to monitor the morphologic effects of neurotoxicity in brain tumor survivors.

Smaller white-matter volumes are associated with larger deficits in attention and learning among long-term survivors of acute lymphoblastic leukemia

BACKGROUND

The primary objective of this study was to test the hypothesis that survivors of childhood acute lymphoblastic leukemia (ALL) have deficits in neurocognitive performance, and smaller white-matter volumes are associated with these deficits.

METHODS

The patients studied included 112 ALL survivors (84 patients who had received chemotherapy only, 28 patients who had received chemotherapy and irradiation; 63 males, 49 females; mean age +/- standard deviation, 4.1 yrs +/- 2.6 yrs at diagnosis; mean +/- standard deviation yrs since diagnosis, 6.0 +/- 3.5 yrs), and 33 healthy siblings who participated as a control group. Neurocognitive tests of attention, intelligence, and academic achievement were performed; and magnetic resonance images were obtained and subsequently were segmented to yield tissue volume measurements. Comparisons of neurocognitive measures and tissue volumes between groups were performed, and the correlations between volumes and neurocognitive performance measures were assessed.

RESULTS

Most performance measures demonstrated statistically significant differences from the normative test scores, but only attention measures exceeded 1.0 standard deviation from normal. Patients who had received chemotherapy alone had significantly larger volumes of white matter than patients who had received treatment that also included cranial irradiation, but their volumes remained significantly smaller than the volumes in the control group. Smaller white-matter volumes were associated significantly with larger deficits in attention, intelligence, and academic achievement.

CONCLUSIONS

Survivors of childhood ALL had significant deficits in attention and smaller white-matter volumes that were associated directly with impaired neurocognitive performance. Cranial irradiation exacerbated these deficits.

Atypical white matter volume development in children following craniospinal irradiation

Most children with medulloblastoma (MB), the second most common pediatric brain tumor, have a 70% probability of survival. However, survivors who receive aggressive therapy are at significant risk of cognitive deficits that have been associated with lower volumes of normal-appearing white matter (NAWM). We hypothesized that cranial irradiation inhibited normal brain volume development in these survivors. We retrospectively analyzed 324 MRI studies of 52 patients with histologically proven MB treated with surgery and 35 to 40 Gy craniospinal irradiation, with or without chemotherapy. The volume of NAWM and that of cerebrospinal fluid were quantified from a single index section and compared with those of healthy, age-similar control subjects. A quadratic random coefficient model was used to identify trends in brain volume with increasing age. Patients treated for MB at younger ages demonstrated substantially less development of NAWM volume than did their healthy peers. Younger age at the time of irradiation and the need for a ventricular shunt were significantly associated with reduced NAWM volume. NAWM and craniospinal fluid volume differences between patients who had shunts and those without resolved over a period of four to five years. NAWM volume is known to be associated with neurocognitive test performance, which shows deficiencies after cranial irradiation early in life. Therefore, volumetric monitoring of brain development can be used to guide the care of survivors, assess the toxicity of previous and current clinical trials, and aid in the design of therapies that minimize toxicity.

Combination of feature-reduced MR spectroscopic and MR imaging data for improved brain tumor classification

The purpose of this paper is to evaluate the effect of the combination of magnetic resonance spectroscopic imaging (MRSI) data and magnetic resonance imaging (MRI) data on the classification result of four brain tumor classes. Suppressed and unsuppressed short echo time MRSI and MRI were performed on 24 patients with a brain tumor and four volunteers. Four different feature reduction procedures were applied to the MRSI data: simple quantitation, principal component analysis, independent component analysis and LCModel. Water intensities were calculated from the unsuppressed MRSI data. Features were extracted from the MR images which were acquired with four different contrasts to comply with the spatial resolution of the MRSI. Evaluation was performed by investigating different combinations of the MRSI features, the MRI features and the water intensities. For each data set, the isolation in feature space of the tumor classes, healthy brain tissue and cerebrospinal fluid was calculated and visualized. A test set was used to calculate classification results for each data set. Finally, the effect of the selected feature reduction procedures on the MRSI data was investigated to ascertain whether it was more important than the addition of MRI information. Conclusions are that the combination of features from MRSI data and MRI data improves the classification result considerably when compared with features obtained from MRSI data alone. This effect is larger than the effect of specific feature reduction procedures on the MRSI data. The addition of water intensities to the data set also increases the classification result, although not significantly. We show that the combination of data from different MR investigations can be very important for brain tumor classification, particularly if a large number of tumors are to be classified simultaneously.

Tissue segmentation and classification of MRSI data using canonical correlation analysis

In this article an accurate and efficient technique for tissue typing is presented. The proposed technique is based on Canonical Correlation Analysis, a statistical method able to simultaneously exploit the spectral and spatial information characterizing the Magnetic Resonance Spectroscopic Imaging (MRSI) data. Recently, Canonical Correlation Analysis has been successfully applied to other types of biomedical data, such as functional MRI data. Here, Canonical Correlation Analysis is adapted for MRSI data processing in order to retrieve in an accurate and efficient way the possible tissue types that characterize the organ under investigation. The potential and limitations of the new technique have been investigated by using simulated as well as in vivo prostate MRSI data, and extensive studies demonstrate a high accuracy, robustness, and efficiency. Moreover, the performance of Canonical Correlation Analysis has been compared to that of ordinary correlation analysis. The test results show that Canonical Correlation Analysis performs best in terms of accuracy and robustness.

Prediction of total cerebral tissue volumes in normal appearing brain from sub-sampled segmentation volumes

The need for anatomical coverage and multi-spectral information must be balanced against examination and processing time to ensure high-quality, feasible imaging protocols for clinical research of cerebral development in normal-appearing brains. The focus of this study was to create and assess models to estimate total cerebral volumes of gray matter, white matter, and cerebrospinal fluid (CSF) from anatomically defined sub-samples of full clinical examinations. Pediatric patients (18F, 11M; aged 1.7 to 18.7, median 5.2 years) underwent a clinical imaging protocol consisting of 3 mm contiguous T1-, T2-, PD-, and FLAIR-weighted images after obtaining informed consent. Magnetic resonance imaging (MRI) sets were registered, RF-corrected, and then analyzed with a hybrid neural network segmentation and classification algorithm to identify normal brain parenchyma. The correlation between the image subsets and the total cerebral volumes of gray matter, white matter and CSF were examined through linear regression analyses. Five sub-sampled sets were defined and assessed in each patient to produce estimation models which were all significantly correlated (p < 0.001) with the total cerebral volumes of gray matter, white matter, and CSF. Volumes were estimated from as little as a single representative slice requiring minimal processing time, 27 min, but with an average estimation error of approximately 6%. Larger sub-samples of approximately three-quarters of the full cerebral volume required much more processing time, 2 h and 4 min, but produced estimates with an average error less than 2%. This study demonstrated that investigators can choose the amount of cerebrum sampled to optimize the acquisition and processing time against the degree of accuracy needed in the total cerebral volume estimates.

Attentional functioning and white matter integrity among survivors of malignant brain tumors of childhood

Children surviving treatment for malignant brain tumors commonly have problems maintaining their premorbid levels of intellectual development and academic achievement. Our group has been especially interested in the effects of treatment on normal appearing white matter (NAWM) on MRI and the influence of NAWM volumes on neurocognitive functioning. The present study assessed NAWM and attentional abilities among 37 long-term survivors of malignant brain tumors, ranging in age from 1.7 to 14.8 (Mdn = 6.5) years at diagnosis, who had been treated with cranial radiation therapy with or without chemotherapy 2.6 to 15.3 (Mdn = 5.7) years earlier. On the Conners' Continuous Performance Test, the Overall Index and 7 of the other 10 indices were significantly deficient compared to age- and gender-corrected normative values. After statistically controlling for the effects of age at diagnosis and time elapsed from treatment, 5 of the 8 indices were significantly associated with cerebral white matter volumes and/or specific regional white matter volumes of the prefrontal/frontal lobe and cingulate gyrus. No gender effects were observed. The results of the present study further support the contention that NAWM is an important substrate for treatment-induced neurocognitive problems among survivors of malignant brain tumors of childhood.

Segmentation of magnetic resonance brain images through discriminant analysis

Segmentation (tissue classification) of medical images obtained from a magnetic resonance (MR) system is a primary step in most applications of medical image post-processing. This paper describes nonparametric discriminant analysis methods to segment multispectral MR images of the brain. Starting from routinely available spin-lattice relaxation time, spin-spin relaxation time, and proton density weighted images (T1w, T2w, PDw), the proposed family of statistical methods is based on: (i) a transform of the images into components that are statistically independent from each other; (ii) a nonparametric estimate of probability density functions of each tissue starting from a training set; (iii) a classic Bayes 0-1 classification rule. Experiments based on a computer built brain phantom (brainweb) and on eight real patient data sets are shown. A comparison with parametric discriminant analysis is also reported. The capability of nonparametric discriminant analysis in improving brain tissue classification of parametric methods is demonstrated. Finally, an assessment of the role of multispectrality in classifying brain tissues is discussed.

A knowledge-guided active contour method of segmentation of cerebella on MR images of pediatric patients with medulloblastoma

PURPOSE

To develop an automated method for identification of the cerebella on magnetic resonance (MR) images of patients with medulloblastoma.

MATERIALS AND METHODS

The method used a template constructed from 10 patients' aligned MR head images, and the contour of this template was superimposed on the aligned data set of a given patient as the starting contour. The starting contour was then actively adjusted to locate the boundary of the cerebellum of the given patient. Morphologic operations were applied to the outlined volume to generate cerebellum images. The method was then applied to data sets of 20 other patients to generate cerebellum images and volumetric results.

RESULTS

Comparison of the automatically generated cerebellum images with two sets of manually traced images showed a strong correlation between the automatically and manually generated volumetric results (correlation coefficient, 0.97). The average Jaccard similarities were 0.89 and 0.88 in comparison to each of two manually traced images, respectively. The same comparisons yielded average kappa indexes of 0.94 and 0.93, respectively.

CONCLUSION

The method was robust and accurate for cerebellum segmentation on MR images of patients with medulloblastoma. The method may be applied to investigations that require segmentation and quantitative measurement of MR images of the cerebellum.

Generalized Kohonen’s competitive learning algorithms for ophthalmological MR image segmentation

Kohonen's self-organizing map is a two-layer feedforward competitive learning network. It has been used as a competitive learning clustering algorithm. In this paper, we generalize Kohonen's competitive learning (KCL) algorithm with fuzzy and fuzzy-soft types called fuzzy KCL (FKCL) and fuzzy-soft KCL (FSKCL). These generalized KCL algorithms fuse the competitive learning with soft competition and fuzzy c-means (FCM) membership functions. We then apply these generalized KCLs to MRI and MRA ophthalmological segmentations. These KCL-based MRI segmentation techniques are useful in reducing medical image noise effects using a learning mechanism. They may be particularly helpful in clinical diagnosis. Two real cases with MR image data recommended by an ophthalmologist are examined. First case is a patient with Retinoblastoma in her left eye, an inborn malignant neoplasm of the retina frequently metastasis beyond the lacrimal cribrosa. The second case is a patient with complete left side oculomotor palsy immediately after a motor vehicle accident. Her brain MRI with MRA, skull routine, orbital CT, and cerebral angiography did not reveal brainstem lesions, skull fractures, or vascular anomalies. These generalized KCL algorithms were used in segmenting the ophthalmological MRIs. KCL, FKCL and FSKCL comparisons are made. Overall, the FSKCL algorithm is recommended for use in MR image segmentation as an aid to small lesion diagnosis.

Brain volumes characterisation using hierarchical neural networks

Objective knowledge of tissue density distribution in CT/MRI brain datasets can be related to anatomical or neuro-functional regions for assessing pathologic conditions characterised by slight differences. The process of monitoring illness and its treatment could be then improved by a suitable detection of these variations. In this paper, we present an approach for three-dimensional (3D) classification of brain tissue densities based on a hierarchical artificial neural network (ANN) able to classify the single voxels of the examined datasets. The method developed was tested on case studies selected by an expert neuro-radiologist and consisting of both normal and pathological conditions. The results obtained were submitted for validation to a group of physicians and they judged the system to be really effective in practical applications.

Developmental model relating white matter volume to neurocognitive deficits in pediatric brain tumor survivors

BACKGROUND

The primary objective of this study was to test the hypothesis that, among survivors of pediatric brain tumors, the association between reduced volumes of normal-appearing white matter (NAWM) and intellectual/academic achievement deficits can be explained by patient problems with memory and attention.

METHODS

Quantitative tissue volumes from magnetic resonance imaging scans and neurocognitive assessments were obtained for 40 long-term survivors of pediatric brain tumors. They were treated with radiotherapy (RT) with or without chemotherapy 2.6-15.3 years earlier (median, 5.7 years) at an age of 1.7-14.8 years (median, 6.5 years). Neurocognitive assessments included standardized tests of intellect (intelligence quotient [IQ]), attention, memory, and academic achievement.

RESULTS

Analyses revealed significant impairments in patients' neurocognitive test performance on all measures. After statistically controlling for age at RT and time from RT, significant associations were found between NAWM volumes and both attentional abilities and IQ, and between attentional abilities and IQ. Subsequent analyses supported the hypothesis that attentional abilities, but not memory, could explain a significant amount of the relationship between NAWM and IQ. The final developmental model predicting academic achievement based on NAWM, attentional abilities, and IQ explained approximately 60% of the variance in reading and spelling and almost 80% of the variance in math.

CONCLUSIONS

The authors demonstrated that the primary consequence of reduced NAWM among pediatric patients treated for brain tumors was decreased attentional abilities, leading to declining IQ and academic achievement.

Multispectral magnetic resonance image analysis using principal component and linear discriminant analysis

PURPOSE

To explore the possibilities of combining multispectral magnetic resonance (MR) images of different patients within one data matrix.

MATERIALS AND METHODS

Principal component and linear discriminant analysis was applied to multispectral MR images of 12 patients with different brain tumors. Each multispectral image consisted of T1-weighted, T2-weighted, proton-density-weighted, and gadolinium-enhanced T1-weighted MR images, and a calculated relative regional cerebral blood volume map.

RESULTS

Similar multispectral image regions were clustered, while dissimilar multispectral image regions were scattered in a single plot. Both principal component and linear discriminant analysis allowed discrimination between healthy and tumor regions on the image. In addition, linear discriminant analysis allowed discrimination between oligodendrogliomas and astrocytomas. However, the discriminant analysis method was partially capable of recognizing the tumor identity in unknown multispectral images.

CONCLUSION

The proposed method may help the radiologist in comparing multispectral MR images of different patients in a more easy and objective way.

Detection of spectral signatures in multispectral MR images for classification

This paper presents a new spectral signature detection approach to magnetic resonance (MR) image classification. It is called constrained energy minimization (CEM) method, which is derived from the minimum variance distortionless response in passive sensor array processing. It considers a bank of spectral channels as an array of sensors where each spectral channel represents a sensor and object spectral signature in multispectral MR images are viewed as signals impinging upon the array. The strength of the CEM lies on its ability in detection of spectral signatures of interest without knowing image background. The detected spectral signatures are then used for classification. The CEM makes use of a finite impulse response (FIR) filter to linearly constrain a desired object while minimizing interfering effects caused by other unknown signal sources. Unlike most spatial-based classification techniques, the proposed CEM takes advantage of spectral characteristics to achieve object detection and classification. A series of experiments is conducted and compared with the commonly used c-means method for performance evaluation. The results show that the CEM method is a promising and effective spectral technique for MR image classification.

Quantitative MRI assessment of leukoencephalopathy

Quantitative MRI assessment of leukoencephalopathy is difficult because the MRI properties of leukoencephalopathy significantly overlap those of normal tissue. This report describes the use of an automated procedure for longitudinal measurement of tissue volume and relaxation times to quantify leukoencephalopathy. Images derived by using this procedure in patients undergoing therapy for acute lymphoblastic leukemia (ALL) are presented. Five examinations from each of five volunteers (25 examinations) were used to test the reproducibility of quantitated baseline and subsequent, normal-appearing images; the coefficients of variation were less than 2% for gray and white matter. Regions of leukoencephalopathy in patients were assessed by comparison with manual segmentation. Two radiologists manually segmented images from 15 randomly chosen MRI examinations that exhibited leukoencephalopathy. Kappa analyses showed that the two radiologists' interpretations were concordant (kappa = 0.70) and that each radiologist's interpretations agreed with the results of the automated procedure (kappa = 0.57 and 0.55). The clinical application of this method was illustrated by analysis of images from sequential MR examinations of two patients who developed leukoencephalopathy during treatment for ALL. The ultimate goal is to use these quantitative MR imaging measures to better understand therapy-induced neurotoxicity, which can be limited or even reversed with some combination of therapy adjustments and pharmacological and neurobehavioral interventions.

Segmentation techniques for tissue differentiation in MRI of ophthalmology using fuzzy clustering algorithms

This paper presents MRI segmentation techniques to differentiate abnormal and normal tissues in Ophthalmology using fuzzy clustering algorithms. Applying the best-known fuzzy c-means (FCM) clustering algorithm, a newly proposed algorithm, called an alternative fuzzy c-mean (AFCM), was used for MRI segmentation in Ophthalmology. These unsupervised segmentation algorithms can help Ophthalmologists to reduce the medical imaging noise effects originating from low resolution sensors and/or the structures that move during the data acquisition. They may be particularly helpful in the clinical oncological field as an aid to the diagnosis of Retinoblastoma, an inborn oncological disease in which symptoms usually show in early childhood. For the purpose of early treatment with radiotherapy and surgery, the newly proposed AFCM is preferred to provide more information for medical images used by Ophthalmologists. Comparisons between FCM and AFCM segmentations are made. Both fuzzy clustering segmentation techniques provide useful information and good results. However, the AFCM method has better detection of abnormal tissues than FCM according to a window selection. Overall, the newly proposed AFCM segmentation technique is recommended in MRI segmentation.

Current methods in medical image segmentation

Image segmentation plays a crucial role in many medical-imaging applications, by automating or facilitating the delineation of anatomical structures and other regions of interest. We present a critical appraisal of the current status of semi-automated and automated methods for the segmentation of anatomical medical images. Terminology and important issues in image segmentation are first presented. Current segmentation approaches are then reviewed with an emphasis on the advantages and disadvantages of these methods for medical imaging applications. We conclude with a discussion on the future of image segmentation methods in biomedical research.

Orthogonal subspace projection-based approaches to classification of MR image sequences

Orthogonal subspace projection (OSP) approach has shown success in hyperspectral image classification. Recently, the feasibility of applying OSP to multispectral image classification was also demonstrated via SPOT (Satellite Pour 1'Observation de la Terra) and Landsat (Land Satellite) images. Since an MR (magnetic resonance) image sequence is also acquired by multiple spectral channels (bands), this paper presents a new application of OSP in MR image classification. The idea is to model an MR image pixel in the sequence as a linear mixture of substances (such as white matter, gray matter, cerebral spinal fluid) of interest from which each of these substances can be classified by a specific subspace projection operator followed by a desired matched filter. The experimental results show that OSP provides a promising alternative to existing MR image classification techniques.

Novel approaches to imaging brain tumors

Brain imaging techniques are assuming a greater range of roles in neuro-oncology. New techniques promise earlier recognition of the spread of tumors to the brain, which is useful in staging of disseminated disease, as well as better definition of small lesions associated with presentations of epilepsy. There is the promise that entirely noninvasive, specific diagnosis of brain tumors may become possible. Imaging methods are being used increasingly to direct and monitor therapy. Preoperative and intraoperative imaging are being used for guiding tumor surgery. An exciting potential goal for greater use of imaging is in the individualization of medical therapies either by analysis of in vitro responses or by visualization of drug responses on the tumor in situ. An important focus for technical development is in the robust integration of complementary information to allow optimization of the sensitivity and specificity of multimodal examinations.

Risks of young age for selected neurocognitive deficits in medulloblastoma are associated with white matter loss

PURPOSE

To test the hypothesis that inadequate development of normal-appearing white matter (NAWM) is associated with the relationship between young age at the time of craniospinal irradiation (CRT) and deficient neurocognitive performance in survivors of childhood medulloblastoma.

PATIENTS AND METHODS

Forty-two patients treated since 1985 participated in this cross-sectional study. All had been treated with CRT with or without chemotherapy and had survived 1 or more years after treatment. Neurocognitive evaluations were conducted with tests of intellect (intelligent quotient; IQ), verbal memory, and sustained attention. Quantitative magnetic resonance imaging, using a hybrid neural network, assessed the volume of NAWM.

RESULTS

Neurocognitive test results were below normal expectations for age at the time of testing. A young age at CRT was significantly associated with worse performance on all neurocognitive tests except that of verbal memory. An increased time from completion of CRT was significantly associated with worse performance on all neurocognitive tests except that of sustained attention. After statistically controlling for the effects of time from CRT, we examined the association of NAWM with neurocognitive test results. These analyses revealed that NAWM accounted for a significant amount of the association between age at CRT and IQ, factual knowledge, and verbal and nonverbal thinking, but not sustained attention or verbal memory.

CONCLUSION

The present results suggest that, at least for some cognitive functions, deficient development and/or loss of NAWM after CRT may provide a neuroanatomical substrate for the adverse impact of a young age at the time of CRT.

Effect of ionizing radiation on the human brain: white matter and gray matter T1 in pediatric brain tumor patients treated with conformal radiation therapy

OBJECTIVE

To test a hypothesis that fractionated radiation therapy (RT) to less than 60 Gy is associated with a dose-related change in the spin-lattice relaxation time (T1) of normal brain tissue, and that such changes are detectable by quantitative MRI (qMRI).

METHODS

Each of 21 patients received a qMRI examination before treatment, and at several time points during and after RT. A map of brain T1 was calculated and segmented into white matter and gray matter at each time point. The RT isodose contours were then superimposed upon the T1 map, and changes in brain tissue T1 were analyzed as a function of radiation dose and time following treatment. We used a mixed-model analysis to analyze the longitudinal trend in brain T1 from the start of RT to 1 year later. Predictive factors evaluated included patient age and clinical variables, such as RT dose, time since treatment, and the use of an imaging contrast agent.

RESULTS

In white matter (WM), a dose level of greater than 20 Gy was associated with a dose-dependent decrease in T1 over time, which became significant about 3 months following treatment. In gray matter (GM), there was no significant change in T1 over time, as a function of RT doses < 60 Gy. However, GM in close proximity to the tumor had an inherently lower T1 before therapy. Neither use of a contrast agent nor a combination of chemotherapy plus steroids had a significant effect on brain T1.

CONCLUSION

Results suggest that T1 mapping may be sensitive to radiation-related changes in human brain tissue T1. WM T1 appears to be unaffected by RT at doses less than approximately 20 Gy; GM T1 does not change at doses less than 60 Gy. However, tumor appears to have an effect upon adjacent GM, even before treatment. Conformal RT may offer a substantial benefit to the patient, by minimizing the volume of normal brain exposed to greater than 20 Gy.

Hybrid artificial neural network segmentation of precise and accurate inversion recovery (PAIR) images from normal human brain

This paper presents a novel semi-automated segmentation and classification method based on raw signal intensities from a quantitative T1 relaxation technique with two novel approaches for the removal of partial volume effects. The segmentation used a Kohonen Self Organizing Map that eliminated inter- and intra-operator variability. A Multi-layered Backpropagation Neural Network was able to classify the test data with a predicted accuracy of 87.2% when compared to manual classification. A linear interpolation of the quantitative T1 information by region and on a pixel-by-pixel basis was used to redistribute voxels containing a partial volume of gray matter (GM) and white matter (WM) or a partial volume of GM and cerebrospinal fluid (CSF) into the principal components of GM, WM, and CSF. The method presented was validated against manual segmentation of the base images by three experienced observers. Comparing segmented outputs directly to the manual segmentation revealed a difference of less than 2% in GM and less than 6% in WM for pure tissue estimations for both the regional and pixel-by-pixel redistribution techniques. This technique produced accurate estimates of the amounts of GM and WM while providing a reliable means of redistributing partial volume effects.

Subtle white matter volume differences in children treated for medulloblastoma with conventional or reduced dose craniospinal irradiation

Medulloblastoma is the most common malignant brain tumor in children, and approximately seventy percent of average-risk patients will achieve long-term survival. Craniospinal irradiation (CSI), combined with chemotherapy and surgery, is currently the mainstay of treatment but places children who survive at risk for serious neurocognitive sequelae. These sequelae are intensified with a younger age at treatment, greater elapsed time following treatment, and an increased radiation dose. Many newer treatment approaches have attempted to address this problem by reducing the dose of the CSI component of radiation therapy while maintaining the current survival rates. This study evaluates longitudinal MR imaging during therapy to assess the impact of the two CSI doses (conventional [36 Gy] and reduced [23.4 Gy]) on normal appearing white matter volumes (NAWMV) evaluated in a single index slice. Twenty-six children and young adults at least three years of age enrolled on an institutional protocol for newly diagnosed, previously untreated primary medulloblastoma had at least four MR examinations over a minimum nine month period following CSI. These serial volumes were evaluated as a function of time since CSI in three analyses: 1) all subjects, 2) subjects stratified by age at CSI, and 3) subjects stratified by CSI dose. The first analysis demonstrated that medulloblastoma patients treated with CSI have a significant loss of NAWMV in contradistiction to normally expected maturation. Stratifying the patients by age at CSI found no significant differences in the rate of NAWMV loss. The final analysis stratified the patients by CSI dose and revealed that the rate of NAWMV loss was 23% slower in children receiving reduced-dose. Serial quantitative MR measures of NAWMV may provide a neuroanatomical substrate for assessing functional impact of CSI on normal brain function following treatment for medulloblastoma.

Periventricular leukomalacia: relationship between lateral ventricular volume on brain MR images and severity of cognitive and motor impairment

PURPOSE

To evaluate the utility of lateral ventricular volume measurements in predicting motor and cognitive impairment severity in children with periventricular leukomalacia (PVL), with or without seizures.

MATERIALS AND METHODS

The charts of children with spastic cerebral palsy and PVL documented on brain magnetic resonance (MR) images were reviewed. Affected children were grouped by motor and cognitive impairment severity and seizure disorder. An age-matched control group was established. Lateral ventricular volumes were measured on two-dimensional T2-weighted spin-echo MR images. Analysis of variance was used to identify significant differences in mean lateral ventricular volume between groups. Paired analyses of differences were performed with the Bonferroni t method.

RESULTS

Thirty-six children (24 boys, 12 girls) with spastic cerebral palsy and PVL and 21 age-matched control subjects (14 boys, seven girls) were identified. Mean lateral ventricular volumes of the moderate and marked motor deficit groups were significantly larger than those of the control and mild motor deficit groups (F = 29.24; alpha = .01). Mean lateral ventricular volumes of all cognitive impairment groups were significantly larger than those of the control and no-cognitive-impairment groups (F = 21.101 alpha = .01). There was no difference in mean lateral ventricular volume between children with PVL with or without seizures.

CONCLUSION

Lateral ventricular volume measurements can be used as quantitative markers of clinical impairment severity and as clinical outcome predictors before formal testing is possible.

Neurocognitive deficits in medulloblastoma survivors and white matter loss

Although previous studies have documented a significant risk of intellectual loss after treatment for childhood medulloblastoma (MED), the pathophysiology underlying this process is poorly understood. The purpose of this study was to test the hypotheses that (1) patients treated for MED in childhood have reduced volumes of normal white matter (NWM) related to their treatment with craniospinal irradiation with or without chemotherapy, and (2) deficits in NWM among patients surviving MED can at least partially explain deficits in their intellectual performance. Eighteen pediatric patients previously treated for MED were matched on the basis of age at the time of evaluation to 18 patients previously treated for low-grade posterior fossa tumors with surgery alone (mean difference, 3.7 months). Evaluations were conducted with age-appropriate neurocognitive testing and quantitative magnetic resonance imaging by using a novel automated segmentation and classification algorithm constructed from a hybrid neural network. Patients treated for MED had significantly less NWM (p < 0.01) and significantly lower Full-Scale IQ values than those treated for low-grade tumors (mean, 82.1 vs 92.9). In addition, NWM had a positive and statistically significant association with Full-Scale IQ among the patients treated for MED. We conclude that irradiation- or chemotherapy-induced destruction of NWM can at least partially explain intellectual and academic achievement deficits among MED survivors.

Hybrid artificial neural network segmentation and classification of dynamic contrast-enhanced MR imaging (DEMRI) of osteosarcoma

The evaluation of pediatric osteosarcoma has suffered from the lack of an accurate imaging measure of response. One major problem is that osteosarcoma do not shrink in response to chemotherapy; instead, viable tumor is replaced by necrotic tissue. Currently available techniques that use dynamic contrast-enhanced magnetic resonance imaging to quantitatively evaluate tumor response fail to assess the percentage of necrosis. At present, histopathologic evaluation of resected tissue is the only means of measuring the percentage of necrosis in treated osteosarcoma. The current study presents a non-invasive method to visualize necrotic and viable tumor and quantitatively assess the response of osteosarcoma. Our technique uses a hybrid neural network consisting of a Kohonen self-organizing map to segment dynamic contrast-enhanced magnetic resonance images and a multi-layer backpropagation neural network to classify the segmented images. Because the hybrid neural network is completely automated, our technique removes both inter- and intra-operator error. An analysis comparing the percentage of necrosis from our technique to the histopathologic analysis revealed a highly significant Spearman correlation coefficient of 0.617 with p < 0.001.

A hybrid neural network analysis of subtle brain volume differences in children surviving brain tumors

In the treatment of children with brain tumors, balancing the efficacy of treatment against commonly observed side effects is difficult because of a lack of quantitative measures of brain damage that can be correlated with the intensity of treatment. We quantitatively assessed volumes of brain parenchyma on magnetic resonance (MR) images using a hybrid combination of the Kohonen self-organizing map for segmentation and a multilayer backpropagation neural network for tissue classification. Initially, we analyzed the relationship between volumetric differences and radiologists' grading of atrophy in 80 subjects. This investigation revealed that brain parenchyma and white matter volumes significantly decreased as atrophy increased, whereas gray matter volumes had no relationship with atrophy. Next, we compared 37 medulloblastoma patients treated with surgery, irradiation, and chemotherapy to 19 patients treated with surgery and irradiation alone. This study demonstrated that, in these patients, chemotherapy had no significant effect on brain parenchyma, white matter, or gray matter volumes. We then investigated volumetric differences due to cranial irradiation in 15 medulloblastoma patients treated with surgery and radiation therapy, and compared these with a group of 15 age-matched patients with low-grade astrocytoma treated with surgery alone. With a minimum follow-up of one year after irradiation, all radiation-treated patients demonstrated significantly reduced white matter volumes, whereas gray matter volumes were relatively unchanged compared with those of age-matched patients treated with surgery alone. These results indicate that reductions in cerebral white matter: 1) are correlated significantly with atrophy; 2) are not related to chemotherapy; and 3) are correlated significantly with irradiation. This hybrid neural network analysis of subtle brain volume differences with magnetic resonance may constitute a direct measure of treatment-induced brain damage.

Ectasia of the basilar artery in children with sickle cell disease: Relationship to hematocrit and psychometric measures

GOAL

To determine whether children with sickle cell disease (SCD), but without clinical evidence of cerebrovascular disease, have vasculopathy shown by quantitative magnetic resonance angiography (MRA).

METHODS

In a retrospective review of MRA films, we compared 47 SCD patients with 49 control patients. Time-of-flight three-dimensional T1-weighted gradient-echo images were reconstructed, by maximum-intensity projection, to show the basilar artery in coronal view, and basilar volume was calculated from measurements made on films. Basilar volume was correlated with hematocrit and with results of cognitive testing.

FINDINGS

Mean basilar artery volume was 74% larger in SCD patients than in controls (P<.001). If the upper limit of normal is defined as mean adult volume +2 SD (< or =427 mm(3)), 2% (1 of 43) of controls but 37% (17 of 46) of SCD patients exceed this value (chi(2)=19.0; P<.001). Basilar volume correlated inversely with hematocrit (r=-.60; P<.0001), with full-scale IQ (r=-.62; P<.005), and with freedom from distractability (r=-.61; P<.006) in SCD patients. Analysis of basilar artery tissue from a 5-year-old SCD patient showed that basilar dilatation can be associated with pathological changes typical of hypertension.

CONCLUSIONS

Approximately 37% of a heterogenous group of pediatric SCD patients had ectasia of the basilar artery. Quantitative MRA is sensitive to subtle vasculopathy that can go undetected in the qualitative analysis more commonly done. Data suggest that there is a substantial elevation of arteriolar blood volume in pediatric SCD patients, and that such patients may share disease features in common with adult hypertension.